Computer Vision and Deep Learning for Activity Recognition

Dear Colleagues,

Human activity recognition (HAR) has gained significant attention due to its wide-ranging applications in healthcare, smart surveillance, human-computer interaction, and autonomous systems. Despite significant progress, challenges such as data scarcity, model generalization, and privacy concerns remain critical barriers to real-world deployment. This Special Issue aims to explore recent advancements in computer vision and deep learning techniques for robust, efficient, and privacy-preserving activity recognition.

Deep learning models, particularly convolutional neural networks (CNNs), recurrent neural networks (RNNs), transformer-based architectures, and graph neural networks (GNNs), have revolutionized HAR by enabling automatic feature extraction and enhanced spatiotemporal pattern recognition. The integration of multimodal data sources, including RGB-D cameras, LiDAR, wearable sensors, and thermal imaging, further enhances the accuracy and adaptability of activity recognition systems. However, challenges such as modality misalignment, missing modalities, and heterogeneous data integration remain open research problems.

This Special Issue invites contributions that address key challenges in HAR, such as real-time processing, occlusion handling, domain adaptation, generalization across diverse environments, and privacy-preserving learning. Topics of interest include, but are not limited to, the following:

• Novel deep learning architectures for activity recognition;
• Self-supervised, few-shot, and federated learning approaches;
• Multimodal fusion techniques for enhanced recognition;
• Explainability and interpretability in deep HAR models;
• Real-time and low-power implementations for edge AI;
• Synthetic data generation and augmentation using generative AI (e.g., diffusion models);
• Human–object interaction modeling and scene understanding;
• Privacy-preserving techniques and federated learning for HAR;
• Applications in healthcare, assistive technologies, surveillance, and emerging fields, such as the metaverse and virtual reality.

We encourage original research articles, review papers, and case studies showcasing innovative methodologies and real-world implementations of computer vision and deep learning in activity recognition. This Special Issue aims to advance the field by fostering interdisciplinary collaborations and discussions on emerging trends, novel solutions, and future directions in HAR.

Dr. Yang Li
Prof. Dr. Hui Yuan
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Applied Sciences is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• human activity recognition
• deep learning
• computer vision
• multimodal fusion
• edge AI
• privacy-preserving learning
• self-supervised learning
• federated learning
• generative AI
• explainable AI